scvi.autotune.ModelTuner#

class scvi.autotune.ModelTuner(model_cls)[source]#

Automated and scalable hyperparameter tuning for scvi-tools models.

Wraps a Tuner instance attached to a scvi-tools model class. Note: this API is in beta and is subject to change in future releases.

Parameters:

model_cls (BaseModelClass) – A model class on which to tune hyperparameters. Must have a class property _tunables that defines tunable elements.

Examples

>>> import anndata
>>> import scvi
>>> adata = anndata.read_h5ad(path_to_h5ad)
>>> model_cls = scvi.model.SCVI
>>> model_cls.setup_anndata(adata)
>>> tuner = scvi.autotune.ModelTuner(model_cls)
>>> results = tuner.fit(adata, metric="validation_loss")

Methods table#

fit(adata, **kwargs)

Run a specified hyperparameter sweep for the associated model class.

info(**kwargs)

Displays a summary of the model class's registry and available resources.

Methods#

fit

ModelTuner.fit(adata, **kwargs)[source]#

Run a specified hyperparameter sweep for the associated model class.

Parameters:

  • adata (Union[AnnData, MuData]) – AnnData or MuData that has been setup with the associated model class.

  • metric – The primary metric to optimize. If not provided, defaults to the model class’s validation loss.

  • additional_metrics – Additional metrics to track during the experiment. Defaults to None.

  • search_space – Dictionary of hyperparameter names and their respective search spaces provided as instantiated Ray Tune sample functions. Available hyperparameters can be viewed with info(). Must be provided if use_defaults is False.

  • use_defaults – Whether to use the model class’s default search space, which can be viewed with info(). If True and search_space is provided, the two will be merged, giving priority to user-provided values. Defaults to False.

  • num_samples – Number of hyperparameter configurations to sample. Defaults to 10.

  • max_epochs – Maximum number of epochs to train each model configuration. Defaults to 100.

  • scheduler –

    Ray Tune scheduler to use. One of the following:

    Note that that not all schedulers are compatible with all search algorithms. See Ray Tune documentation for more details.

  • scheduler_kwargs – Keyword arguments to pass to the scheduler.

  • searcher –

    Ray Tune search algorithm to use. One of the following:

  • searcher_kwargs – Keyword arguments to pass to the search algorithm.

  • reporter –

    Whether to display progress with a Ray Tune reporter. Defaults to True. Depending on the execution environment, one of the following:

  • resources –

    Dictionary of maximum resources to allocate for the experiment. Available keys include:

    • "cpu": number of CPU threads

    • "gpu": number of GPUs

    • "memory": amount of memory

    If not provided, defaults to using all available resources. Note that fractional allocations are supported.

  • experiment_name – Name of the experiment, used for logging purposes. Defaults to a unique string with the format "tune_{model_cls}_{timestamp}".

  • logging_dir – Directory to store experiment logs. Defaults to a directory named ray in the current working directory.

Returns:

TuneAnalysis A dataclass containing the results of the tuning experiment.

Return type:

None

info

ModelTuner.info(**kwargs)[source]#

Displays a summary of the model class’s registry and available resources.

Parameters:

  • show_additional_info – Whether to show additional information about the model class’s registry.

  • show_resources – Whether to show available resources.

Return type:

None